LLMs for Unit Test Generation This is a great survey on the use of LLM for unit test generation. It proposes a taxonomy based on the unit test generation lifecycle that divides the process into a generative phase for creating test artifacts and a quality assurance phase for refining them. Paper: Learn how to build effective AI agents in our academy:

NEW Survey: AI Agents for Scientific Discovery. This is one of the most exciting areas going into 2026. (bookmark this one) This new research introduces SAGA (Scientific Autonomous Goal-evolving Agent), a bi-level framework where the outer loop automatically evolves objectives while the inner loop optimizes solutions. Why is this paper a big deal? Scientific discovery requires iterating on what to optimize, not just how to optimize. Automating this objective evolution loop closes a gap that has bottlenecked most of the recent AI-driven science research. Instead of treating objective design as a one-time human decision, SAGA makes it a dynamic, autonomous discovery process. An LLM-based planner proposes new objectives. An implementer converts them into executable scoring functions. An optimizer searches for solutions. An analyzer examines results and identifies where objectives need refinement. SAGA operates at three automation levels: > co-pilot mode, where scientists collaborate on objective evolution > semi-pilot where scientists only provide feedback to the analyzer > autopilot where both analysis and planning are fully automated Results across four scientific domains: In antibiotic design for drug-resistant K. pneumoniae, SAGA achieves the best balance between biological activity and drug-likeness. While baselines either fail to optimize activity or achieve high activity with chemically unrealistic molecules, SAGA dynamically adds objectives like synthesizability penalties and metabolic stability filters based on analyzing population-level trends. In materials design, SAGA found 15 novel stable structures for permanent magnets with low supply chain risk within 200 DFT calculations, outperforming MatterGen (11 structures). For superhard materials, over 90% of proposed crystals contain light elements essential for hardness, aligning with experimental findings. In DNA sequence design, SAGA surpasses baselines on cell-type-specific enhancer design by up to 176%, with 48% improvement in specificity and 47% in motif enrichment. In chemical process design, SAGA identifies that optimizing only for product purity leads to unnecessarily complex flowsheets, then autonomously adds objectives for capital costs and material flow intensity. Paper: Learn to build effective AI Agents in our academy: